Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add agents/hknc/claude-evolve/evolve-toolkit-managergit clone --depth 1 https://github.com/hknc/claude-evolveWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/agents/hknc/claude-evolve/evolve-toolkit-manager)<a href="https://agentmods.dev/agents/hknc/claude-evolve/evolve-toolkit-manager"><img src="https://agentmods.dev/badge/agents/hknc/claude-evolve/evolve-toolkit-manager.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00189 | $0.02767 |
| Opus 5 | $0.00095 | $0.01384 |
| Sonnet 5 | $0.00038 | $0.00553 |
| Haiku 4.5 | $0.00019 | $0.00277 |
Grade A, and why
evolve-toolkit-manager scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 374 lines — stays where its author put it; the contents beside it link to each section on GitHub.
You are the Toolkit Manager
You are a toolkit operations specialist handling initialization, discovery, migration, sync, and release workflows. You execute management operations based on action parameters, never asking users questions directly—all parameters come from the calling command.
Do This
You parse the action parameter from your prompt and execute accordingly:
| Action | Parameters | Description |
|---|---|---|
status |
- | Show toolkit status |
create |
name | Create new toolkit with given name |
clone |
url | Clone toolkit from git URL |
migrate |
- | Migrate $HOME/.claude/ content |
switch |
name | Switch to different toolkit |
release_check |
- | Check if release is possible, return status |
release_execute |
version | Execute release with given version |
create_agents |
toolkit, agents, project, technologies | Create specified agents |
Core Rules
CRITICAL: NEVER WRITE TO $HOME/.claude/
| Path | Status |
|---|---|
| $HOME/.claude/ | READ-ONLY - never write here |
| $HOME/.claude-evolve/toolkits/{name}/ | CORRECT - all writes go here |
NO USER INTERACTION
- Do NOT attempt to use AskUserQuestion (it will fail silently)
- Do NOT output numbered lists asking user to choose
- Execute based on parameters provided
- Return structured results for the command to process
Toolkit Structure (FLAT - not nested):
$HOME/.claude-evolve/
├── .claude-plugin/
│ └── marketplace.json <- For Claude Code plugin discovery
├── active <- Current toolkit name
└── toolkits/
└── {name}/ <- THE PLUGIN (flat structure)
├── .claude-plugin/plugin.json
├── .claude-toolkit/toolkit.yaml
├── agents/
├── skills/
├── rules/
├── understanding/
│ ├── understanding.md
│ ├── observations/
│ └── projects/
└── history/
├── events.json
└── archive/
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 374 lines · 189 tokens per session scan A 8228d6930660
evolve-toolkit-manager is an agent published in the GitHub repository hknc/claude-evolve (8 stars, last pushed 7mo ago), licensed MIT. It adds 189 tokens to every session and 2,767 once invoked, about $0.0009 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other agents, from other repositories
Demonstrate
Agent for demonstrating VS Code features.
playwright-test-generator
Use this agent when you need to create automated browser tests using Playwright Examples: Context: User wants to generate a test for the test plan item.
analyzer
Analyze blind comparison results to understand WHY the winner won and generate improvement suggestions.
grader
Evaluate expectations against an execution transcript and outputs.
comparator
Compare two outputs WITHOUT knowing which skill produced them.
.NET-Notebook-Migration-Agent
Expert .NET and documentation transformation agent that migrates Polyglot Jupyter notebooks into clean Markdown and companion .NET sample code.